On 31/10/2019 17:02, Janne Johansson
wrote:
I thought about protecting everything
with a proper full ratio, but I really afraid of the perspective
of some human error (raising fullratio too high to help to recover
some 'very important data asap') which would leave cluster broken
for real. Those few Gb would be the next line of defense. It's
better to have a downtime than 'unable to recover' situation.
Den tors 31 okt. 2019 kl 15:07 skrev George Shuklin <george.shuklin@xxxxxxxxx>:
Thank you everyone, I got it. There is no way to fix out-of-space
bluestore without expanding it.
Therefore, in production we would stick with 99%FREE size for LV, as it
gives operators 'last chance' to repair the cluster in case of
emergency. It's a bit unfortunate that we need to give up the whole per
cent (1 % is too much for 4Tb drives).
In production, stuff with start giving warnings at 85%, so you would just not get into this kinds of situations where the last percent matters or not.
_______________________________________________ ceph-users mailing list ceph-users@xxxxxxxxxxxxxx http://lists.ceph.com/listinfo.cgi/ceph-users-ceph.com
